angerhang
angerhang
Currently, our sample.cwa file might be a bit too large for a simple test especially when one is trying to troubleshoot end-to-end.
To do be done after this https://github.com/activityMonitoring/biobankAccelerometerAnalysis/pull/117 is merged :D
BBAA is a multi-stage processing tool with Java and Python interleaving each other. Despite our effort to move towards pythonize everything, it would take time and the underlying processing pipeline...
@angerhang, how would you feel about merging this and then adding the test separately? I would like to use this soon... _Originally posted by @R-Walmsley in https://github.com/activityMonitoring/biobankAccelerometerAnalysis/issues/91#issuecomment-746237471_ This PR was...
https://github.com/activityMonitoring/biobankAccelerometerAnalysis/blob/0b3879386b06fc4bd41714b91de1ba59c34b892d/accelerometer/summariseEpoch.py#L275-L280 Currently `quality-goodWearTime` only supports hard-coded threshold which is not ideal.
Thanks @chanshing for bringing this up. > Just to double check, is this line correct?: >https://github.com/activityMonitoring/biobankAccelerometerAnalysis/blame/6021de453950e464737373cd62ea7c6a6af3a391/java/ActigraphReader.java#L479 > Also, I see that in some parts firstSampleTime is multplied by 1000 to...
1. Get the sample files for all the supported accelerometer file types 2. Generate the epoch files as reference 3. Create a testing workflow
As Shing pointed out, our current way of calculating the correlation might suffer from catastrophic cancellation. Good to update to a more stable algorithm for covariance. Even though we don't...
At the moment we can only support one flow out. Is there any plans to include `parallel` node type or even limited support? I am trying to draw something very...